{"id":"https://openalex.org/W1670456408","doi":"https://doi.org/10.1109/icacci.2015.7275698","title":"Novel self-learning based crawling and data mining for automatic information extraction","display_name":"Novel self-learning based crawling and data mining for automatic information extraction","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W1670456408","doi":"https://doi.org/10.1109/icacci.2015.7275698","mag":"1670456408"},"language":"en","primary_location":{"id":"doi:10.1109/icacci.2015.7275698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icacci.2015.7275698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Novel_self-learning_based_crawling_and_data_mining_for_automatic_information_extraction/26062657","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025326058","display_name":"Arun Kumar A V","orcid":null},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Arun Kumar A V","raw_affiliation_strings":["Tata Consultancy Services, CTO Networks Lab, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Tata Consultancy Services, CTO Networks Lab, Bangalore, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041222815","display_name":"Hemant Kumar Rath","orcid":"https://orcid.org/0000-0003-0729-9028"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant Kumar Rath","raw_affiliation_strings":["Tata Consultancy Services, CTO Networks Lab, Bangalore, India","CTO Networks Lab, Tata Consultancy Services, Bangalore, India#TAB#"],"affiliations":[{"raw_affiliation_string":"Tata Consultancy Services, CTO Networks Lab, Bangalore, India","institution_ids":["https://openalex.org/I55215948"]},{"raw_affiliation_string":"CTO Networks Lab, Tata Consultancy Services, Bangalore, India#TAB#","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112051922","display_name":"Shameemraj M Nadaf","orcid":null},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shameemraj M Nadaf","raw_affiliation_strings":["Tata Consultancy Services, CTO Networks Lab, Bangalore, India","CTO Networks Lab, Tata Consultancy Services, Bangalore, India#TAB#"],"affiliations":[{"raw_affiliation_string":"Tata Consultancy Services, CTO Networks Lab, Bangalore, India","institution_ids":["https://openalex.org/I55215948"]},{"raw_affiliation_string":"CTO Networks Lab, Tata Consultancy Services, Bangalore, India#TAB#","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086713842","display_name":"Anantha Simha","orcid":null},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anantha Simha","raw_affiliation_strings":["Tata Consultancy Services, CTO Networks Lab, Bangalore, India","CTO Networks Lab, Tata Consultancy Services, Bangalore, India#TAB#"],"affiliations":[{"raw_affiliation_string":"Tata Consultancy Services, CTO Networks Lab, Bangalore, India","institution_ids":["https://openalex.org/I55215948"]},{"raw_affiliation_string":"CTO Networks Lab, Tata Consultancy Services, Bangalore, India#TAB#","institution_ids":["https://openalex.org/I55215948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025326058"],"corresponding_institution_ids":["https://openalex.org/I55215948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.05549185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"732","last_page":"738"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9832000136375427,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9728999733924866,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.8961098194122314},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8210051655769348},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6406369209289551},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6078532338142395},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5287356376647949},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.5033645033836365},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.47954651713371277},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4725853204727173},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4595971703529358},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3711528778076172},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.29984748363494873},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.17299345135688782}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8961098194122314},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8210051655769348},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6406369209289551},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6078532338142395},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5287356376647949},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.5033645033836365},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.47954651713371277},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4725853204727173},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4595971703529358},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3711528778076172},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29984748363494873},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.17299345135688782},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icacci.2015.7275698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icacci.2015.7275698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI)","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/26062657","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Novel_self-learning_based_crawling_and_data_mining_for_automatic_information_extraction/26062657","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/26062657","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Novel_self-learning_based_crawling_and_data_mining_for_automatic_information_extraction/26062657","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1570448133","https://openalex.org/W2048170153","https://openalex.org/W2086339938","https://openalex.org/W2125969310"],"related_works":["https://openalex.org/W4393220254","https://openalex.org/W4321258516","https://openalex.org/W2051833850","https://openalex.org/W2016355461","https://openalex.org/W2386938185","https://openalex.org/W2068844411","https://openalex.org/W1986386500","https://openalex.org/W2793744252","https://openalex.org/W1516746680","https://openalex.org/W2072284316"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"techniques":[5,22,60,130],"using":[6],"a":[7,32],"novel":[8],"combination":[9],"of":[10,88,102],"self-learning":[11],"based":[12,16,109,133],"crawling":[13,21],"and":[14,53,65,92,99,114,120,135],"rule":[15],"data":[17,25,36,51,106],"mining.":[18],"Using":[19],"the":[20,49,97,103],"smaller":[23],"relevant":[24],"sets":[26,37,52],"can":[27,66],"be":[28,67],"obtained":[29],"pertaining":[30],"to":[31,55,96,122],"domain":[33],"from":[34],"multi-dimensional":[35],"available":[38],"in":[39,63,73,124],"on-line":[40],"as":[41,43,77],"well":[42],"off-line":[44],"sources.":[45],"We":[46,126],"then":[47],"process":[48],"crawled":[50],"mine":[54],"extract":[56],"meaningful":[57],"information.":[58],"Our":[59],"are":[61,87,118],"generic":[62],"nature":[64,101],"used":[68],"for":[69],"automatic":[70],"information":[71],"extraction":[72],"different":[74],"domains":[75],"such":[76],"biomedical,":[78],"health-care,":[79],"enterprise":[80,140],"infrastructure":[81],"planning,":[82],"etc.":[83],"The":[84,105],"proposed":[85,129],"schemes":[86],"reduced":[89],"time,":[90],"space":[91],"processor":[93],"complexity":[94],"due":[95],"assisted":[98],"learning":[100],"crawling.":[104],"mining":[107],"is":[108],"on":[110],"configurable":[111],"classification":[112],"rules":[113],"decision":[115],"trees,":[116],"which":[117],"scalable":[119],"easy":[121],"implement":[123],"practice.":[125],"evaluate":[127],"our":[128],"through":[131],"Java":[132],"implementation":[134],"integration":[136],"with":[137],"TCS":[138],"in-house":[139],"network":[141],"design":[142],"tool":[143],"NetDes.":[144]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
